skills.rest
vellum-ai
vellum-aiOFFICIAL
Explore all skills by this author →
Website𝕏@vellum_aiGitHub

image-studio

Generate and edit images from text prompts with optional source images.

1.0k|158|Updated Feb 7, 2026
Search Tags:#design#editing#image#ai#visuals#prompts#generate
One-click install
npx skills add https://github.com/vellum-ai/vellum-assistant --skill image-studio-vellum-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-studio
Source: https://github.com/vellum-ai/vellum-assistant/tree/main/assistant/src/config/bundled-skills/image-studio
Command: npx skills add https://github.com/vellum-ai/vellum-assistant --skill image-studio-vellum-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-powered image creation and editing can be time-consuming and requires multiple tools; this skill streamlines generating new visuals and editing existing images through prompts and optional source files.

Core Features & Use Cases

  • Generate new images from text prompts with optional model variations and style guidance.
  • Edit an existing image by applying changes described in prompts using source images as references.
  • Create multiple variants of a design (logos, concept art, product visuals) to compare options quickly.

Quick Start

Prompt the AI to generate an image or edit an existing image using an optional source image.

Frequently Asked Questions about image-studio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images from text prompts?▼

To generate AI images from text prompts, you provide a descriptive text prompt to the image generation tool, which then creates new visuals based on your input. You can also include optional model variations and style guidance to refine the output.

Can I edit an existing image using AI prompts?▼

Yes, you can edit an existing image by providing the source image and describing the desired changes in a text prompt. The AI applies the modifications to the source image to produce the updated visual.

How do I create multiple variations of a design like a logo or concept art?▼

You can create multiple variations of a design by prompting the AI to generate different options for logos, concept art, or product visuals. This allows you to quickly compare multiple design iterations from a single prompt.

Do I need a source image to generate new AI visuals?▼

No, you do not need a source image to generate new AI visuals. Source images are optional and are only required if you want to edit an existing image or use it as a reference for precise modifications.

What happens if there are configuration or credentials errors during image generation?▼

If configuration or credentials errors occur during image generation, the skill includes error handling to manage these issues. This ensures the image generation or editing process fails gracefully instead of crashing unexpectedly.

Related Skills

Explore More Design & Creative Skills→
byteplus-sabyteplus-sa
8

polym-eval-generate-gemini

Generate PNG images from text prompts using Google Gemini/Imagen or ByteDance AIDP backends.

Official
Intermediate
Yezez9Yezez9

pptx-posters

Generate research posters in PPTX format from HTML/CSS templates.

Community
Advanced
Emily2040Emily2040
6.3k

seedance-antislop

Removes vague language from prompts for visual and auditory AI models.

Community
Intermediate
SunS1eep1ngSunS1eep1ng

imagegen

Generate and edit bitmap images using AI models via API.

Community
Advanced